TY - GEN
T1 - Classification of software behaviors for failure detection
T2 - 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '09
AU - Lo, David
AU - Cheng, Hong
AU - Han, Jiawei
AU - Khoo, Siau Cheng
AU - Sun, Chengnian
PY - 2009
Y1 - 2009
N2 - Software is a ubiquitous component of our daily life. We often depend on the correct working of software systems. Due to the difficulty and complexity of software systems, bugs and anomalies are prevalent. Bugs have caused billions of dollars loss, in addition to privacy and security threats. In this work, we address software reliability issues by proposing a novel method to classify software behaviors based on past history or runs. With the technique, it is possible to generalize past known errors and mistakes to capture failures and anomalies. Our technique first mines a set of discriminative features capturing repetitive series of events from program execution traces. It then performs feature selection to select the best features for classification. These features are then used to train a classifier to detect failures. Experiments and case studies on traces of several benchmark software systems and a real-life concurrency bug from MySQL server show the utility of the technique in capturing failures and anomalies. On average, our pattern-based classification technique out-performs the baseline approach by 24.68% in accuracy 1.
AB - Software is a ubiquitous component of our daily life. We often depend on the correct working of software systems. Due to the difficulty and complexity of software systems, bugs and anomalies are prevalent. Bugs have caused billions of dollars loss, in addition to privacy and security threats. In this work, we address software reliability issues by proposing a novel method to classify software behaviors based on past history or runs. With the technique, it is possible to generalize past known errors and mistakes to capture failures and anomalies. Our technique first mines a set of discriminative features capturing repetitive series of events from program execution traces. It then performs feature selection to select the best features for classification. These features are then used to train a classifier to detect failures. Experiments and case studies on traces of several benchmark software systems and a real-life concurrency bug from MySQL server show the utility of the technique in capturing failures and anomalies. On average, our pattern-based classification technique out-performs the baseline approach by 24.68% in accuracy 1.
KW - Algorithms
KW - Experimentation
UR - http://www.scopus.com/inward/record.url?scp=69449099775&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=69449099775&partnerID=8YFLogxK
U2 - 10.1145/1557019.1557083
DO - 10.1145/1557019.1557083
M3 - Conference contribution
AN - SCOPUS:69449099775
SN - 9781605584959
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 557
EP - 565
BT - KDD '09
Y2 - 28 June 2009 through 1 July 2009
ER -